The frontier model now thinks in silence for half an hour. gpt-6 astra's system card, highlighted…
the frontier model now thinks in silence for half an hour. gpt-6 astra's system card, highlighted september 8, shows silent reasoning time climbing from 3.6 to 30.9 minutes, while openai's chief scientist warns monitoring is failing.
the black box got blacker.
Context
OpenAI's GPT-6 Astra page on its Deployment Safety Hub, published 3 September 2026 with a 9 September revision to one section, says Astra's monitorability has decreased relative to GPT-5.6 Sol, that Astra is more capable of controlling its own chain of thought than Sol, and that Astra class models could evade chain-of-thought monitors under adversarial conditions, with findings largely based on adversarial evaluations in which the model is instructed to evade monitoring.
Lower monitorability than GPT-5.6 Sol is first-party and mostly under adversarial tests. The figures 3.6 and 30.9 minutes were not found in the text read, which is a partial render of a long page, so they are unverified. Highlighted September 8 was not found, since the card is dated 3 September with a 9 September revision. A chief scientist quote that monitoring is failing was not found, and the card's wording about adversarial evasion and reduced monitorability is narrower than failing.
Watch next
- The system card section on reasoning duration and the source of the chief scientist statement.
Sources
- GPT-6 Astra (OpenAI Deployment Safety Hub)deploymentsafety.openai.com
- GPT-6 Astra (OpenAI)openai.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 21 September 2026 at 11:09 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →